Popular repositories Loading

1. websearch-benchmark websearch-benchmark Public

   Open benchmark comparing web-search engines (Tavily, Exa, Firecrawl) vs LLM-native web search on quality (LLM-as-judge), cost, and latency. Reproducible, fully logged, one-file adapters.

   Python 5

2. runtoken runtoken Public

   A blazing-fast BPE tokenizer for LLMs. Drop-in tiktoken replacement, 20-80x faster.

   Python 3

3. requesty-chat requesty-chat Public

   TypeScript

4. AI-kart AI-kart Public

   JavaScript

5. hermes-agent hermes-agent Public

   Forked from NousResearch/hermes-agent

   The agent that grows with you

   Python